Evaluating a clinically available artificial intelligence model for intracranial aneurysm detection: a…

AI / informaticsNeuroradiology· Apr 2025

Evaluating a clinically available artificial intelligence model for intracranial aneurysm detection: a multi-reader study and algorithmic audit.

Bin Hu, Haitao He, Zhao Shi … Longjiang Zhang

Medical Imaging AIAI / informaticsDiagnosisQ2IF 2.9

Artificial intelligence assistance raised general radiologists' aneurysm detection performance on CT angiography

Evaluating a clinically available artificial intelligence model for intracranial aneurysm detection: a multi-reader study and algorithmic audit.

Bin Hu … Longjiang Zhang

Neuroradiology · Apr 2025

Purpose

We aimed to validate a clinically available artificial intelligence (artificial intelligence) model to assist general radiologists in the detection of intracranial aneurysm (intracranial aneurysm) in a multi-reader multi-case (multi-reader multi-case) study, and to explore its performance in routine clinical settings.

Methods

Cohort 1, comprising gold-standard consecutive CT angiography cases, was used in an multi-reader multi-case study involving six board-certified general radiologists.

n = 131 CTA cases

AUC 0.815 to 0.875

Results

AUC 0.815 to 0.875

Artificial intelligence assistance raised radiologists' detection accuracy, AUROC nearer to 1.0 means better performance

n = 131 CTA cases

More results

Cohort 1 consisted of 131 CT angiography cases, while Cohort 2 included 515 CT angiography cases.

In the artificial intelligence-based first-reader study, 60.4% of the CT angiography cases were identified as negative by the artificial intelligence, with a high negative predictive value of 0.994 (95%CI: 0.977-0.999).

“

Conclusion · 1 of 2

This study highlights the clinical utility of a high-performance artificial intelligence model in detecting IAs, significantly improving general radiologists' diagnostic performance with the potential to reduce their workload in routine clinical practice.

Conclusion · 2 of 2

The algorithmic audit offers insights to guide the development and validation of future artificial intelligence models.

Evaluating a clinically available artificial intelligence model for intracranial aneurysm detection: a multi-reader study and algorithmic audit.

Evaluating a clinically available artificial intelligence model for intracranial aneurysm detection: a multi-reader study and algorithmic audit.

Related papers